Leveraging Self-supervised Denoising for Image Segmentation
This addresses the challenge of expensive and scarce annotated data for biomedical image segmentation, though it is incremental as it builds on existing methods.
The paper tackles the problem of limited annotated training data and noise in microscopy image segmentation by using self-supervised denoising networks to enhance segmentation methods, showing consistent improvements in segmentation quality, particularly with limited noisy data.
Deep learning (DL) has arguably emerged as the method of choice for the detection and segmentation of biological structures in microscopy images. However, DL typically needs copious amounts of annotated training data that is for biomedical projects typically not available and excessively expensive to generate. Additionally, tasks become harder in the presence of noise, requiring even more high-quality training data. Hence, we propose to use denoising networks to improve the performance of other DL-based image segmentation methods. More specifically, we present ideas on how state-of-the-art self-supervised CARE networks can improve cell/nuclei segmentation in microscopy data. Using two state-of-the-art baseline methods, U-Net and StarDist, we show that our ideas consistently improve the quality of resulting segmentations, especially when only limited training data for noisy micrographs are available.